New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Some questions need to be consulted #4

Open

FrankyTang opened this issue Nov 25, 2024 · 0 comments

FrankyTang commented Nov 25, 2024

why batch_stride is 0, not seq_q * head_q * dim in ops/flash_attn_v2.cpp(line 39)
params.q_batch_stride = 0;
params.k_batch_stride = 0;
params.v_batch_stride = 0;
After using TensorRT for encapsulation, I found that the values of other nodes were modified. But the result of compute-sanitizer is ok. How to analyze the reasons next.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment